[R-package] [docs] Simplified examples to cut example run time (fixes m…

…icrosoft#2988) (microsoft#2989) * [R-package] [docs] Simplified examles to cut example run time (fixes microsoft#2988) * updated learning rates
jameslamb · Apr 15, 2020 · 1816167 · 1816167
1 parent 151bf07
commit 1816167
Show file tree

Hide file tree

Showing 46 changed files with 132 additions and 124 deletions.
diff --git a/R-package/R/lgb.Booster.R b/R-package/R/lgb.Booster.R
@@ -711,7 +711,6 @@ Booster <- R6::R6Class(
 #'         number of columns corresponding to the number of trees.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -723,11 +722,10 @@ Booster <- R6::R6Class(
 #' model <- lgb.train(
 #'   params = params
 #'   , data = dtrain
-#'   , nrounds = 10L
+#'   , nrounds = 5L
 #'   , valids = valids
 #'   , min_data = 1L
 #'   , learning_rate = 1.0
-#'   , early_stopping_rounds = 5L
 #' )
 #' preds <- predict(model, test$data)
 #' @export
@@ -769,7 +767,7 @@ predict.lgb.Booster <- function(object,
 #' @return lgb.Booster
 #'
 #' @examples
-#' library(lightgbm)
+#' \donttest{
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -781,17 +779,17 @@ predict.lgb.Booster <- function(object,
 #' model <- lgb.train(
 #'   params = params
 #'   , data = dtrain
-#'   , nrounds = 10L
+#'   , nrounds = 5L
 #'   , valids = valids
 #'   , min_data = 1L
 #'   , learning_rate = 1.0
-#'   , early_stopping_rounds = 5L
+#'   , early_stopping_rounds = 3L
 #' )
 #' lgb.save(model, "model.txt")
 #' load_booster <- lgb.load(filename = "model.txt")
 #' model_string <- model$save_model_to_string(NULL) # saves best iteration
 #' load_booster_from_str <- lgb.load(model_str = model_string)
-#'
+#' }
 #' @export
 lgb.load <- function(filename = NULL, model_str = NULL) {
 
@@ -828,6 +826,7 @@ lgb.load <- function(filename = NULL, model_str = NULL) {
 #' @return lgb.Booster
 #'
 #' @examples
+#' \donttest{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -847,6 +846,7 @@ lgb.load <- function(filename = NULL, model_str = NULL) {
 #'   , early_stopping_rounds = 5L
 #' )
 #' lgb.save(model, "model.txt")
+#' }
 #' @export
 lgb.save <- function(booster, filename, num_iteration = NULL) {
 
@@ -874,6 +874,7 @@ lgb.save <- function(booster, filename, num_iteration = NULL) {
 #' @return json format of model
 #'
 #' @examples
+#' \donttest{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -893,7 +894,7 @@ lgb.save <- function(booster, filename, num_iteration = NULL) {
 #'   , early_stopping_rounds = 5L
 #' )
 #' json_model <- lgb.dump(model)
-#'
+#' }
 #' @export
 lgb.dump <- function(booster, num_iteration = NULL) {
 
@@ -922,7 +923,6 @@ lgb.dump <- function(booster, num_iteration = NULL) {
 #'
 #' @examples
 #' # train a regression model
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -934,11 +934,10 @@ lgb.dump <- function(booster, num_iteration = NULL) {
 #' model <- lgb.train(
 #'   params = params
 #'   , data = dtrain
-#'   , nrounds = 10L
+#'   , nrounds = 5L
 #'   , valids = valids
 #'   , min_data = 1L
 #'   , learning_rate = 1.0
-#'   , early_stopping_rounds = 5L
 #' )
 #'
 #' # Examine valid data_name values

diff --git a/R-package/R/lgb.Dataset.R b/R-package/R/lgb.Dataset.R
@@ -725,7 +725,6 @@ Dataset <- R6::R6Class(
 #' @return constructed dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -770,7 +769,6 @@ lgb.Dataset <- function(data,
 #' @return constructed dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -797,7 +795,6 @@ lgb.Dataset.create.valid <- function(dataset, data, info = list(), ...) {
 #' @param dataset Object of class \code{lgb.Dataset}
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -828,7 +825,6 @@ lgb.Dataset.construct <- function(dataset) {
 #' be directly used with an \code{lgb.Dataset} object.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -863,7 +859,6 @@ dim.lgb.Dataset <- function(x, ...) {
 #' Since row names are irrelevant, it is recommended to use \code{colnames} directly.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -936,7 +931,6 @@ dimnames.lgb.Dataset <- function(x) {
 #' @return constructed sub dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -983,7 +977,6 @@ slice.lgb.Dataset <- function(dataset, idxset, ...) {
 #' }
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1037,7 +1030,6 @@ getinfo.lgb.Dataset <- function(dataset, name, ...) {
 #' }
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1078,7 +1070,6 @@ setinfo.lgb.Dataset <- function(dataset, name, info, ...) {
 #' @return passed dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1109,7 +1100,6 @@ lgb.Dataset.set.categorical <- function(dataset, categorical_feature) {
 #' @return passed dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package ="lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1141,7 +1131,6 @@ lgb.Dataset.set.reference <- function(dataset, reference) {
 #' @return passed dataset
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.cv.R b/R-package/R/lgb.cv.R
@@ -56,19 +56,17 @@ CVBooster <- R6::R6Class(
 #' @return a trained model \code{lgb.CVBooster}.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #' params <- list(objective = "regression", metric = "l2")
 #' model <- lgb.cv(
 #'   params = params
 #'   , data = dtrain
-#'   , nrounds = 10L
+#'   , nrounds = 5L
 #'   , nfold = 3L
 #'   , min_data = 1L
 #'   , learning_rate = 1.0
-#'   , early_stopping_rounds = 5L
 #' )
 #' @importFrom data.table data.table setorderv
 #' @export

diff --git a/R-package/R/lgb.importance.R b/R-package/R/lgb.importance.R
@@ -13,20 +13,22 @@
 #' }
 #'
 #' @examples
-#' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #'
 #' params <- list(
 #'   objective = "binary"
-#'   , learning_rate = 0.01
-#'   , num_leaves = 63L
+#'   , learning_rate = 0.1
 #'   , max_depth = -1L
 #'   , min_data_in_leaf = 1L
 #'   , min_sum_hessian_in_leaf = 1.0
 #' )
-#' model <- lgb.train(params, dtrain, 10L)
+#' model <- lgb.train(
+#'     params = params
+#'     , data = dtrain
+#'     , nrounds = 5L
+#' )
 #'
 #' tree_imp1 <- lgb.importance(model, percentage = TRUE)
 #' tree_imp2 <- lgb.importance(model, percentage = FALSE)

diff --git a/R-package/R/lgb.interprete.R b/R-package/R/lgb.interprete.R
@@ -16,7 +16,6 @@
 #'         Contribution columns to each class.
 #'
 #' @examples
-#' Sigmoid <- function(x) 1.0 / (1.0 + exp(-x))
 #' Logit <- function(x) log(x / (1.0 - x))
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -27,13 +26,16 @@
 #'
 #' params <- list(
 #'     objective = "binary"
-#'     , learning_rate = 0.01
-#'     , num_leaves = 63L
+#'     , learning_rate = 0.1
 #'     , max_depth = -1L
 #'     , min_data_in_leaf = 1L
 #'     , min_sum_hessian_in_leaf = 1.0
 #' )
-#' model <- lgb.train(params, dtrain, 10L)
+#' model <- lgb.train(
+#'     params = params
+#'     , data = dtrain
+#'     , nrounds = 3L
+#' )
 #'
 #' tree_interpretation <- lgb.interprete(model, test$data, 1L:5L)
 #'

diff --git a/R-package/R/lgb.plot.importance.R b/R-package/R/lgb.plot.importance.R
@@ -24,17 +24,19 @@
 #'
 #' params <- list(
 #'     objective = "binary"
-#'     , learning_rate = 0.01
-#'     , num_leaves = 63L
-#'     , max_depth = -1L
+#'     , learning_rate = 0.1
 #'     , min_data_in_leaf = 1L
 #'     , min_sum_hessian_in_leaf = 1.0
 #' )
 #'
-#' model <- lgb.train(params, dtrain, 10L)
+#' model <- lgb.train(
+#'     params = params
+#'     , data = dtrain
+#'     , nrounds = 5L
+#' )
 #'
 #' tree_imp <- lgb.importance(model, percentage = TRUE)
-#' lgb.plot.importance(tree_imp, top_n = 10L, measure = "Gain")
+#' lgb.plot.importance(tree_imp, top_n = 5L, measure = "Gain")
 #' @importFrom graphics barplot par
 #' @export
 lgb.plot.importance <- function(tree_imp,

diff --git a/R-package/R/lgb.plot.interpretation.R b/R-package/R/lgb.plot.interpretation.R
@@ -15,28 +15,43 @@
 #' The \code{lgb.plot.interpretation} function creates a \code{barplot}.
 #'
 #' @examples
-#' library(lightgbm)
-#' Sigmoid <- function(x) {1.0 / (1.0 + exp(-x))}
-#' Logit <- function(x) {log(x / (1.0 - x))}
+#' \donttest{
+#' Logit <- function(x) {
+#'   log(x / (1.0 - x))
+#' }
 #' data(agaricus.train, package = "lightgbm")
-#' train <- agaricus.train
-#' dtrain <- lgb.Dataset(train$data, label = train$label)
-#' setinfo(dtrain, "init_score", rep(Logit(mean(train$label)), length(train$label)))
+#' labels <- agaricus.train$label
+#' dtrain <- lgb.Dataset(
+#'   agaricus.train$data
+#'   , label = labels
+#' )
+#' setinfo(dtrain, "init_score", rep(Logit(mean(labels)), length(labels)))
+#'
 #' data(agaricus.test, package = "lightgbm")
-#' test <- agaricus.test
 #'
 #' params <- list(
 #'   objective = "binary"
-#'   , learning_rate = 0.01
-#'   , num_leaves = 63L
+#'   , learning_rate = 0.1
 #'   , max_depth = -1L
 #'   , min_data_in_leaf = 1L
 #'   , min_sum_hessian_in_leaf = 1.0
 #' )
-#' model <- lgb.train(params, dtrain, 10L)
+#' model <- lgb.train(
+#'   params = params
+#'   , data = dtrain
+#'   , nrounds = 5L
+#' )
 #'
-#' tree_interpretation <- lgb.interprete(model, test$data, 1L:5L)
-#' lgb.plot.interpretation(tree_interpretation[[1L]], top_n = 10L)
+#' tree_interpretation <- lgb.interprete(
+#'   model = model
+#'   , data = agaricus.test$data
+#'   , idxset = 1L:5L
+#' )
+#' lgb.plot.interpretation(
+#'   tree_interpretation_dt = tree_interpretation[[1L]]
+#'   , top_n = 5L
+#' )
+#' }
 #' @importFrom data.table setnames
 #' @importFrom graphics barplot par
 #' @export

diff --git a/R-package/R/lgb.prepare.R b/R-package/R/lgb.prepare.R
@@ -8,7 +8,6 @@
 #'         for input in \code{lgb.Dataset}.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(iris)
 #'
 #' str(iris)

diff --git a/R-package/R/lgb.prepare2.R b/R-package/R/lgb.prepare2.R
@@ -11,7 +11,6 @@
 #'         for input in \code{lgb.Dataset}.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(iris)
 #'
 #' str(iris)

diff --git a/R-package/R/lgb.prepare_rules.R b/R-package/R/lgb.prepare_rules.R
@@ -10,7 +10,6 @@
 #'         in \code{lgb.Dataset}.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(iris)
 #'
 #' str(iris)

diff --git a/R-package/R/lgb.prepare_rules2.R b/R-package/R/lgb.prepare_rules2.R
@@ -13,7 +13,6 @@
 #'         \code{lgb.Dataset}.
 #'
 #' @examples
-#' library(lightgbm)
 #' data(iris)
 #'
 #' str(iris)